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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overarching
    -0.08
    .lu
    -0.07
    <l
    -0.07
    <r
    -0.07
    <Service
    -0.07
    Р
    -0.07
    atLng
    -0.07
    Telefono
    -0.06
    -ts
    -0.06
    ṝ
    -0.06
    POSITIVE LOGITS
    ⛏
    0.08
     suicide
    0.07
     enhance
    0.07
    }},↵
    0.07
     suction
    0.07
     自
    0.06
     �
    0.06
    합니다
    0.06
     [...]
    0.06
    ✳
    0.06
    Act Density 0.018%

    No Known Activations