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

    Neuronpedia

    INDEX
    Explanations

    radical or ROS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logistic
    -0.07
     Floor
    -0.06
     Serialized
    -0.06
     forest
    -0.06
    ices
    -0.06
     Slovenia
    -0.06
     yours
    -0.06
    stores
    -0.06
    _LOW
    -0.06
     eyes
    -0.06
    POSITIVE LOGITS
    .ReadByte
    0.07
    -aware
    0.06
    _fitness
    0.06
    �
    0.06
     pne
    0.06
    skyt
    0.06
    周期
    0.06
    whole
    0.06
    .placeholder
    0.06
     "~
    0.06
    Act Density 0.014%

    No Known Activations