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

    Neuronpedia

    INDEX
    Explanations

    define/form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reshape
    -0.07
    拴
    -0.06
    spell
    -0.06
     continue
    -0.06
    ldap
    -0.06
    (con
    -0.06
     prefetch
    -0.06
     rushes
    -0.06
     completa
    -0.06
    ɒ
    -0.06
    POSITIVE LOGITS
    etri
    0.08
    uition
    0.07
    .EqualTo
    0.07
    傀
    0.07
    🙋
    0.07
    _geometry
    0.07
    ɥ
    0.07
    0.06
    		↵		↵
    0.06
    "profile
    0.06
    Act Density 0.026%

    No Known Activations