Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phil

    np_max-act · gemini-2.0-flash

    The neuron activates on word fragments denoting hydrophilic (“phil”) or hydrophobic (“ph-/phob”) chemical characteristics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nêu
    -0.07
    NSNotification
    -0.07
    ','=',$
    -0.07
    ==
    -0.07
     뭐
    -0.06
    CppObject
    -0.06
    .'</
    -0.06
    ộ
    -0.06
     velice
    -0.06
    }}">↵
    -0.06
    POSITIVE LOGITS
    ivist
    0.08
     spirit
    0.08
    arity
    0.07
     processing
    0.07
    Wallet
    0.06
     educating
    0.06
     denial
    0.06
     viewing
    0.06
     Any
    0.06
     利
    0.06
    Act Density 0.001%

    No Known Activations