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

    Neuronpedia

    INDEX
    Explanations

    weak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _invalid
    -0.07
     Supplements
    -0.07
     NP
    -0.07
    _INIT
    -0.06
     descriptors
    -0.06
     mythical
    -0.06
    Compilation
    -0.06
    _dataset
    -0.06
    (ac
    -0.06
    	Query
    -0.06
    POSITIVE LOGITS
     konum
    0.07
    ::::::::::::::::::::::::::::::::
    0.07
     Punch
    0.07
     Вели
    0.07
    Dick
    0.07
     Vel
    0.07
    этому
    0.06
    으면
    0.06
    า�
    0.06
    посеред
    0.06
    Act Density 0.001%

    No Known Activations