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

    Neuronpedia

    INDEX
    Explanations

    medical experiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tracking
    -0.08
     Hide
    -0.07
     believing
    -0.07
    DEPEND
    -0.07
     Rivers
    -0.07
    Ports
    -0.07
     molded
    -0.07
     destination
    -0.07
     Rewrite
    -0.06
     interface
    -0.06
    POSITIVE LOGITS
    ΩΣ
    0.06
    /li
    0.06
     rowspan
    0.06
     feasible
    0.05
    _dates
    0.05
    orary
    0.05
    كار
    0.05
    �
    0.05
    .decrypt
    0.05
     semiclass
    0.05
    Act Density 0.037%

    No Known Activations