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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chilly
    -0.07
     drawback
    -0.06
     부
    -0.06
    >If
    -0.06
     miejs
    -0.06
     �
    -0.06
    สล
    -0.06
     이용
    -0.06
    浅
    -0.06
     possibly
    -0.06
    POSITIVE LOGITS
    JB
    0.06
    (control
    0.06
     который
    0.06
    вест
    0.06
     mAuth
    0.06
     balk
    0.06
    LOGGER
    0.06
    _
↵
↵
    0.06
     storytelling
    0.06
     dlg
    0.06
    Act Density 0.000%

    No Known Activations