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

    Neuronpedia

    INDEX
    Explanations

    code licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [next
    -0.07
    lém
    -0.06
    fax
    -0.06
    яем
    -0.06
    _mag
    -0.06
    らしい
    -0.06
     branching
    -0.06
    هره
    -0.06
     이것
    -0.06
     badge
    -0.06
    POSITIVE LOGITS
     преп
    0.08
    Cl
    0.07
    _DIALOG
    0.06
     filt
    0.06
     reimb
    0.06
    templ
    0.06
    Signing
    0.06
    �
    0.06
    /filter
    0.06
     inclined
    0.06
    Act Density 0.000%

    No Known Activations