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

    Neuronpedia

    INDEX
    Explanations

    chip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сон
    -0.08
    沃
    -0.06
     Ko
    -0.06
     audiences
    -0.06
     Buen
    -0.06
     Â
    -0.06
     hoc
    -0.06
    Optional
    -0.06
     xb
    -0.06
    _data
    -0.06
    POSITIVE LOGITS
     teeth
    0.07
     flush
    0.07
     alright
    0.07
    ile
    0.07
     дет
    0.07
     lecken
    0.06
    -java
    0.06
    ahren
    0.06
     opens
    0.06
    碰
    0.06
    Act Density 0.000%

    No Known Activations